© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 11-RES-JB
    11. 15713
    Prev
    Next
    INDEX
    Explanations

    mentions of the Central Intelligence Agency (CIA)

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the CIA and its officials

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Mulcair
    -0.79
    £ı
    -0.74
    amaz
    -0.73
    icles
    -0.72
    kees
    -0.71
    nings
    -0.69
    ghai
    -0.68
    abeth
    -0.68
     Ys
    -0.68
    igans
    -0.67
    POSITIVE LOGITS
     Director
    1.10
     operative
    1.00
    Director
    0.95
     operatives
    0.94
    CIA
    0.94
     Headquarters
    0.94
     annex
    0.93
     director
    0.93
    andestine
    0.89
     Directors
    0.89
    Activations Density 0.043%

    No Known Activations